Instructions to use tachion/tower-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tachion/tower-ai with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tachion/tower-ai
# Run inference directly in the terminal:
llama cli -hf tachion/tower-ai

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tachion/tower-ai
# Run inference directly in the terminal:
llama cli -hf tachion/tower-ai

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tachion/tower-ai
# Run inference directly in the terminal:
./llama-cli -hf tachion/tower-ai

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tachion/tower-ai
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tachion/tower-ai

Use Docker

docker model run hf.co/tachion/tower-ai

LM Studio
Jan
Ollama
How to use tachion/tower-ai with Ollama:
```
ollama run hf.co/tachion/tower-ai
```
Unsloth Desktop

How to use tachion/tower-ai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tachion/tower-ai

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tachion/tower-ai"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tachion/tower-ai with Docker Model Runner:
```
docker model run hf.co/tachion/tower-ai
```

Lemonade

How to use tachion/tower-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tachion/tower-ai

Run and chat with the model

lemonade run user.tower-ai-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use tachion/tower-ai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tachion/tower-ai

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tachion/tower-ai

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tachion/tower-ai with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tachion/tower-ai

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "tachion/tower-ai" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

tower-ai-v2 by yAI

Tower for RC Planes, for a better flight simulation.

Ollama Page

Here you can find the Ollama page for more details.

GitHub Page

Here you can find the GitHub page for more details.

YouTube Video

Here you can find the YouTube video tutorial.

yAI website

Here you can find the official yAI website.

AI Model

TowerAI is a custom LLM model based on LLaMA3.2 3B. Thanks to OLLaMA and the custom AI model, it's working at least 36.36% faster than the old version which uses the Gemini 1.5 Flash API. Also, the old version uses WiFi, and this model can work on an average laptop locally. It doesn't need supercomputers; it has only 3B parameters. It works perfectly on a MacBook Air 2017 and Lenovo ThinkPad. You can even use Nvidia's new Jetson Nano Super for improved portability. Of course, it's not tested, and it should work 99%.

Software

There are 2 programs. One of them is the API, and the other is the AI. The AI uses our custom TowerAI model, which is recommended. It's faster and better. It runs locally. The other one is the Gemini 1.5 Flash API. You need a custom API key, etc., for that, and it needs an internet connection. You can test them both to see the performance of our TowerAI model.

What software does

It converts Speech-To-Text first. Then it sends the result to the chosen AI model as a prompt. After that, it converts the response into a regular sound file (as mp3). Then it adds a radio effect to it to improve the experience. So it feels like you are really talking with the tower.

Install TowerAI v2 3B

Install:

ollama pull MYusuf/tower-ai

Install and run for testing directly:

ollama run MYusuf/tower-ai

See Installed Model:

ollama list

There should be tower-ai!

Installation

Clone the repository:

git clone https://github.com/MYusufY/tower-ai-v2.git
cd tower-ai-v2

Install the requirements
```
pip install -r requirements.txt
```
(OPTIONAL) Switch to "myenv" which has all the required libraries and setup

You can install the venv to directly have all required libraries installed instead using requirements.txt. You can find myenv from old repo.
```
source myenv/bin/activate
```
Run the AI/API script

TowerAI custom model:
```
python3 tower-ai-custom.py
```
To run the tower-ai-custom.py script, you need to install TowerAI v2 3B model first!

Google Gemini 1.5 Flash API:
```
python3 tower-ai-api.py
```
Set API key (if you are using Gemini) To get an API key, you can follow the steps of my LVGL Gemini project.

Contact

You can contact us here: tachion.software@gmail.com

Downloads last month: 4

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support